Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 3583 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 3.3831. Min Range: -3.3831

Max Act: 3.3831. Min Act: -0.0000

Data Index: 1054623 (C4 (Web Text))

Max Activating Token Index: 57

Text #1

Max Range: 3.3831. Min Range: -3.3831

Max Act: 3.2258. Min Act: -0.0000

Data Index: 333452 (C4 (Web Text))

Max Activating Token Index: 612

Text #2

Max Range: 3.3831. Min Range: -3.3831

Max Act: 2.8220. Min Act: -0.0000

Data Index: 408034 (C4 (Web Text))

Max Activating Token Index: 339

Text #3

Max Range: 3.3831. Min Range: -3.3831

Max Act: 2.9600. Min Act: -0.0000

Data Index: 653013 (C4 (Web Text))

Max Activating Token Index: 995

Text #4

Max Range: 3.3831. Min Range: -3.3831

Max Act: 2.5854. Min Act: -0.0000

Data Index: 1101800 (C4 (Web Text))

Max Activating Token Index: 260

Text #5

Max Range: 3.3831. Min Range: -3.3831

Max Act: 2.7243. Min Act: -0.0000

Data Index: 976497 (C4 (Web Text))

Max Activating Token Index: 830

Text #6

Max Range: 3.3831. Min Range: -3.3831

Max Act: 2.5736. Min Act: -0.0000

Data Index: 315764 (C4 (Web Text))

Max Activating Token Index: 425

Text #7

Max Range: 3.3831. Min Range: -3.3831

Max Act: 2.4182. Min Act: -0.0000

Data Index: 949348 (C4 (Web Text))

Max Activating Token Index: 813

Text #8

Max Range: 3.3831. Min Range: -3.3831

Max Act: 2.0486. Min Act: -0.0000

Data Index: 1234 (C4 (Web Text))

Max Activating Token Index: 871

Text #9

Max Range: 3.3831. Min Range: -3.3831

Max Act: 2.2574. Min Act: -0.0000

Data Index: 506975 (C4 (Web Text))

Max Activating Token Index: 279

Text #10

Max Range: 3.3831. Min Range: -3.3831

Max Act: 2.2500. Min Act: -0.0000

Data Index: 731331 (C4 (Web Text))

Max Activating Token Index: 626

Text #11

Max Range: 3.3831. Min Range: -3.3831

Max Act: 2.1086. Min Act: -0.0000

Data Index: 675182 (C4 (Web Text))

Max Activating Token Index: 605

Text #12

Max Range: 3.3831. Min Range: -3.3831

Max Act: 2.2104. Min Act: -0.0000

Data Index: 200715 (C4 (Web Text))

Max Activating Token Index: 416

Text #13

Max Range: 3.3831. Min Range: -3.3831

Max Act: 1.9471. Min Act: -0.0000

Data Index: 590238 (C4 (Web Text))

Max Activating Token Index: 891

Text #14

Max Range: 3.3831. Min Range: -3.3831

Max Act: 2.0369. Min Act: -0.0000

Data Index: 1358183 (C4 (Web Text))

Max Activating Token Index: 60

Text #15

Max Range: 3.3831. Min Range: -3.3831

Max Act: 2.2213. Min Act: -0.0000

Data Index: 308445 (C4 (Web Text))

Max Activating Token Index: 945

Text #16

Max Range: 3.3831. Min Range: -3.3831

Max Act: 2.0912. Min Act: -0.0000

Data Index: 912184 (C4 (Web Text))

Max Activating Token Index: 782

Text #17

Max Range: 3.3831. Min Range: -3.3831

Max Act: 2.2987. Min Act: -0.0000

Data Index: 240673 (C4 (Web Text))

Max Activating Token Index: 416

Text #18

Max Range: 3.3831. Min Range: -3.3831

Max Act: 2.2226. Min Act: -0.0000

Data Index: 1247453 (C4 (Web Text))

Max Activating Token Index: 840

Text #19

Max Range: 3.3831. Min Range: -3.3831

Max Act: 1.9978. Min Act: -0.0000

Data Index: 310158 (C4 (Web Text))

Max Activating Token Index: 430